Commit Graph

5 Commits

Author SHA1 Message Date
Agent Zero cfb4c5ae8b Phase 5.1-5.4: PWA, Public Plugin Endpoints, Contacts Embedding, Search Coverage
Check Cross-Plugin Imports / check (push) Has been cancelled
5.1 Public Plugin Endpoints:
- PluginRouteDef.is_public field in manifest.py
- main.py: public routes mounted without auth dependency
- permissions/public_routes.py: token-based share link access (info, verify, download)
- permissions/plugin.py: public share route registered with is_public=True

5.2 PWA:
- vite.config.ts: VitePWA plugin configured (autoUpdate, workbox, runtime caching)
- frontend/public/manifest.json: PWA manifest with icons
- index.html: theme-color, manifest link, apple-touch-icon, apple-mobile-web-app meta
- Build generates sw.js + workbox (90 precache entries)

5.3 Contacts Embedding:
- contact.py: embedding column (Vector(768)) added to Contact model
- Migration 0002_embeddings.sql already exists (adds embedding + HNSW index)
- ContactSearchProvider already queries embedding column

5.4 Search Coverage:
- 5 new search providers: task, contactperson, tag, conversation, user
- All providers implement FTS search with tenant_id + deleted_at filters
- TagSearchProvider also supports vector search (384-dim embedding)
- provider_registry.py: all 5 new providers auto-registered
- Total: 10 search providers (was 5)
2026-08-04 14:49:35 +02:00
Agent Zero 517e1b6d8b sprint2+3: remaining services visibility filter + search provider permission-aware + dashboard route
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-07-29 02:05:14 +02:00
Agent Zero 879106c4eb Phase 1C: Frontend unified contact UI 2026-07-23 17:17:32 +02:00
Agent Zero c670846cbd Update unified search providers for unified contacts model (company queries contacts with type=company) 2026-07-19 21:32:24 +02:00
Agent Zero 8cebb4f4e9 feat: unified_search + ai_proactive plugins with Ollama Cloud DeepSeek V4
- unified_search: Hybride Suche (PostgreSQL FTS + pgvector + RRF Fusion)
  - 5 Search Providers (Contact, Company, Mail, File, Event)
  - KI Query Understanding (Fuzzy, Facetten via LiteLLM)
  - DMS Text-Extraction (PDF, DOCX, XLSX, PPTX)
  - Embedding Pipeline (ollama/nomic-embed-text, 768 Dim)
  - Background Jobs für Indexierung
  - Plugin-basierte Provider Registry

- ai_proactive: Proaktiver KI-Agent
  - Context-Tracking (Frontend → Backend → Event Bus)
  - Proactive Engine mit LLM Suggestion-Generierung
  - SSE Real-time Push an Frontend
  - 6 AI Tools für Tool Registry
  - Rate-Limiting + User Settings
  - Deep Analysis Background Jobs

- Frontend Integration:
  - useAIContext Hook, SuggestionSidebar, SuggestionBadge
  - ProactiveAISettings Page, Search API Client
  - Globale Suche auf neue API umgestellt

- Tests: test_unified_search.py + test_ai_proactive.py (alle bestanden)
- Config: Ollama Cloud DeepSeek V4 als Default, konfigurierbar
- Dependencies: PyMuPDF, python-docx, python-pptx, pgvector
- Bugfixes: notification type_key length, migration IF NOT EXISTS
2026-07-18 11:21:51 +02:00